4.1: Introduction

Last updated
Save as PDF

Page ID: 30967

\( \newcommand{\vecs}[1]{\overset { \scriptstyle \rightharpoonup} {\mathbf{#1}} } \) \( \newcommand{\vecd}[1]{\overset{-\!-\!\rightharpoonup}{\vphantom{a}\smash {#1}}} \)\(\newcommand{\id}{\mathrm{id}}\) \( \newcommand{\Span}{\mathrm{span}}\) \( \newcommand{\kernel}{\mathrm{null}\,}\) \( \newcommand{\range}{\mathrm{range}\,}\) \( \newcommand{\RealPart}{\mathrm{Re}}\) \( \newcommand{\ImaginaryPart}{\mathrm{Im}}\) \( \newcommand{\Argument}{\mathrm{Arg}}\) \( \newcommand{\norm}[1]{\| #1 \|}\) \( \newcommand{\inner}[2]{\langle #1, #2 \rangle}\) \( \newcommand{\Span}{\mathrm{span}}\) \(\newcommand{\id}{\mathrm{id}}\) \( \newcommand{\Span}{\mathrm{span}}\) \( \newcommand{\kernel}{\mathrm{null}\,}\) \( \newcommand{\range}{\mathrm{range}\,}\) \( \newcommand{\RealPart}{\mathrm{Re}}\) \( \newcommand{\ImaginaryPart}{\mathrm{Im}}\) \( \newcommand{\Argument}{\mathrm{Arg}}\) \( \newcommand{\norm}[1]{\| #1 \|}\) \( \newcommand{\inner}[2]{\langle #1, #2 \rangle}\) \( \newcommand{\Span}{\mathrm{span}}\)\(\newcommand{\AA}{\unicode[.8,0]{x212B}}\)

This chapter provides the information necessary to design, carry out, and analyze the results of a simulation experiment. Experimentation with a simulation model, as opposed to an exact analytic solution obtained using mathematics, is required. Principle 2 states that simulation models conform both to system structure and to available system data. Conditional logic is employed. Thus, these models usually cannot be solved by analytic methods. Simulation experiments must be properly designed and conducted as would any field or laboratory experiment. The design of simulation experiments leads to the benefits of simulation described by principle 3: lower cost and more flexibility than physical prototypes as well as less risk of negative consequence on day-to-day operations than direct experimentation with existing, operating systems as the plan-do-check-act (PDCA) cycle of lean would do.

The design of a simulation experiment specifies how model processing generates the information needed to address the issues and to meet the solution objectives identified in the first phase of the simulation process. An approach to the analysis of results is presented, including ways of examining simulation results to help understand system behavior as well as the use of statistical methods such as confidence interval estimation to help obtain evidence about performance, including the comparison of scenarios.

Prerequisite issues to the design and analysis of any simulation experiment are discussed. These include verification and validation as well as the need to construct independent observations of simulation performance measures and to distinguish between probability and degree of confidence.

Verification and validation are discussed first followed by a discussion of the need to construct independent observations of performance measures. The design elements of simulation experiments are explained. Finally, an approach to the analysis of terminating simulation results is given along with an explanation of how probability and degree of confidence are differentiated.

The discussion in this chapter assumes some prior knowledge of data summarization, probability, and confidence interval estimation.